Offline Skill Graph (OSG): A Framework for Learning and Planning using Offline Reinforcement Learning Skills

TL;DR

This paper introduces the Offline Skill Graph framework, enabling reinforcement learning agents to learn from offline data and plan over skills for complex, real-world tasks, demonstrated on a robotic arm.

Contribution

The paper presents a novel framework that combines offline skill learning with planning, addressing the gap in applying reinforcement learning to real-world scenarios.

Findings

Successfully applied to a robotic arm for complex tasks

Enables planning over offline learned skills

Addresses real-world application limitations

Abstract

Reinforcement Learning has received wide interest due to its success in competitive games. Yet, its adoption in everyday applications is limited (e.g. industrial, home, healthcare, etc.). In this paper, we address this limitation by presenting a framework for planning over offline skills and solving complex tasks in real-world environments. Our framework is comprised of three modules that together enable the agent to learn from previously collected data and generalize over it to solve long-horizon tasks. We demonstrate our approach by testing it on a robotic arm that is required to solve complex tasks.